Intelligent scheduling method for water conservancy facilities based on levy flight optimization and BIM

Abstract

The application discloses a kind of water conservancy facilities intelligent scheduling methods based on Lévy flight optimization and BIM, comprising the following steps: S1. the full life cycle digital three-dimensional model of target water conservancy facilities is constructed on BIM platform;S2. the real-time monitoring data set of target water conservancy facilities is collected, and the real-time monitoring data set collected is mapped with full life cycle digital three-dimensional model;S3. the optimization framework of scheduling problem is formed;S4. the control parameter of Lévy flight optimization algorithm is initialized;S5. global search is carried out on scheduling problem using Lévy flight optimization algorithm, and a plurality of candidate scheduling schemes are generated in optimization model using random jump and adaptive adjustment mechanism;S6. the optimal scheduling scheme is selected, and the selected optimal scheduling scheme is mapped to the control system of target water conservancy facilities, to generate corresponding scheduling control instruction.The application greatly improves the intelligence, adaptability and operability of water conservancy facilities scheduling system.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of water conservancy, and particularly relates to a water conservancy facility intelligent scheduling method based on Lévy flight optimization and BIM. BACKGROUND

[0002] With the continuous development of digital twins and information technology in the field of infrastructure, water conservancy facility management gradually moves towards intelligent and digital transformation. As a core component of the national water resource allocation, flood control and disaster reduction, and irrigation and water supply system, the scientificity and real-time performance of the scheduling management of water conservancy facilities are directly related to the regional water safety and operation efficiency.

[0003] In the prior art, water conservancy facility scheduling generally relies on rule bases, expert experience and static mathematical models for decision-making. Although such methods have certain adaptability under specific working conditions, they are difficult to cope with the high dynamicity and uncertainty of current environmental conditions. Specifically, firstly, traditional scheduling models are usually established under static assumptions, lack real-time state updating mechanisms during facility operation, and are difficult to respond quickly to sudden floods, droughts and equipment failures. Secondly, the structural constraints, operation logic and device semantic information of water conservancy facilities are often not fully integrated in scheduling decisions, making it difficult to implement scheduling schemes. Thirdly, most scheduling optimization algorithms are based on local search strategies or linear programming methods, which are prone to local optimization when dealing with high-dimensional, nonlinear and multi-constrained problems, and are difficult to obtain global solutions to scheduling problems.

[0004] On the other hand, although building information modeling (BIM) has been popularized in water conservancy engineering design, construction and management in recent years, its deep integration at the scheduling decision level is still weak. Currently, BIM is more used for visual display and structural collaborative management, and its massive operation data and component semantic information have not been effectively utilized for intelligent generation and optimization of scheduling strategies. In addition, existing scheduling systems often do not build high-coupling data channels with BIM models, leading to data update delays and information fragmentation problems, further restricting the real-time performance and scientificity of scheduling schemes.

[0005] Therefore, it is urgent to propose a new water conservancy facility intelligent scheduling method that integrates BIM technology and intelligent optimization algorithms, has structural constraint adaptability, real-time response capability and global search capability, to effectively solve the above technical bottlenecks. SUMMARY

[0006] One object of the present application is to provide a water conservancy facility intelligent scheduling method based on Lévy flight optimization and BIM, which greatly improves the intelligence, adaptability and operability of the water conservancy facility scheduling system.

[0007] According to an embodiment of the present application, a water conservancy facility intelligent scheduling method based on Lévy flight optimization and BIM comprises the following steps:

[0008] S1. Construct a full-life-cycle digital three-dimensional model of the target water conservancy facility on a BIM platform;

[0009] S2. Collect a real-time monitoring data set of the target water conservancy facility, and perform data mapping between the collected real-time monitoring data set and the full-life-cycle digital three-dimensional model to realize dynamic updating of the full-life-cycle digital three-dimensional model data;

[0010] S3. Based on the data dynamically updated in the BIM platform, extract the current operation state information and scheduling boundary conditions of the target water conservancy facility, and establish an optimization model of the water conservancy facility scheduling problem to form an optimization framework of the scheduling problem;

[0011] S4. Initialize the control parameters of the Lévy flight optimization algorithm, and generate an initial solution group according to the scheduling problem optimization model extracted in the BIM platform, and simultaneously introduce an adaptive step adjustment mechanism based on BIM semantic constraints;

[0012] S5. Perform global search on the scheduling problem by using the Lévy flight optimization algorithm, generate multiple candidate scheduling schemes in the optimization model by using a random jump and adaptive adjustment mechanism, and perform mapping verification on each candidate scheduling scheme by using the BIM platform;

[0013] S6. Perform comprehensive evaluation on the candidate scheduling schemes according to a preset scheduling target, select an optimal scheduling scheme, and map the selected optimal scheduling scheme to a control system of the target water conservancy facility to generate a corresponding scheduling control instruction.

[0014] Optionally, the S1 comprises the following steps:

[0015] S11. Obtain an engineering design data set of the target water conservancy facility, the engineering design data set comprising structural member number, geometric size, material type and spatial position parameters, use the engineering design data set as a structure basis for constructing the full-life-cycle digital three-dimensional model, and construct a structure information matrix;

[0016] S12. Access a real-time operation monitoring system of the target water conservancy facility, collect a historical and current operation state data set, including water level monitoring values, flow records, pump station states, gate opening and closing states and equipment start and stop time operation parameters, and construct an operation state information matrix;

[0017] S13. Based on a real-time environment perception system of a water conservancy facility operation area, collect an environmental parameter data set, including rainfall intensity, evaporation amount, temperature, wind speed and soil humidity, which are external environmental information affecting the operation of the water conservancy facility, and construct an environmental parameter matrix;

[0018] S14. Extract the set of key scheduling parameters, which includes facility operating capacity limit, scheduling time window, response delay limit and operation frequency constraint, and create a key scheduling parameter constraint vector.

[0019] S15. Transfer the structural information matrix M structure Operating status information matrix M status Environmental parameter matrix M env and the key scheduling parameter constraint vector P key Integrating into the BIM platform to construct a digital 3D model of the target water conservancy facility throughout its entire lifecycle. BIM

[0020] M BIM = <M structure M status M env ,P key >

[0021] Optionally, S2 includes the following steps:

[0022] S21. Real-time monitoring system based on water conservancy facility deployment collects real-time monitoring data streams. Each data d t Including the current water level h t Traffic q t Equipment status s t Valve status v t and environmental parameter set E t Construct real-time monitoring data vectors:

[0023] d t =(h t ,q t ,s t ,v t E t );

[0024] S22. Transfer the real-time monitoring data stream D real With structural information matrix M structure and the running status information matrix M status Perform time tag alignment, mapping the data to the full lifecycle digital 3D model M in the BIM platform based on the acquisition time t. BIM For the corresponding running node, construct the time-state mapping function:

[0025] f map :d t →M BIM (t);

[0026] Among them, f maprepresents a real-time data mapping function, so that each set of real-time monitoring data is injected into the corresponding scheduling unit node;

[0027] S23. The running state information matrix M in the BIM platform is dynamically updated status according to the set time update period, and the new monitoring data vector d t is added to the updated running state information matrix:

[0028]

[0029] wherein, represents the running state information matrix before time t, and represents the updated state information;

[0030] S24. The updated running state information matrix M is jointly injected into the BIM platform with the current window data E env of the environmental parameter matrix M t to dynamically update the full life cycle digital three-dimensional model

[0031]

[0032] Optionally, the S3 comprises the following steps:

[0033] S31. Based on the full life cycle digital three-dimensional model dynamically updated in the BIM platform , the running state information of the target water conservancy facility at the current time is extracted, and the current running state information vector is defined, which includes the water level state at the current time, the flow state at the current time, the current equipment running state, the current valve opening and closing state, and the current time environmental parameter set;

[0034] S32. Based on the key scheduling parameter constraint vector P key , the current scheduling boundary condition is extracted, including the upper limit of the scheduling capacity of the target water conservancy facility, the allowed scheduling time window, the response delay limit and the operation frequency constraint, and the scheduling constraint condition set C boundary is constructed;

[0035] S33. According to the running state information vector X t+Δt and the scheduling constraint condition set C boundary , an optimization model of the water conservancy facility scheduling problem is established, and the optimization model defines the state space of the scheduling scheme as:

[0036]

[0037] wherein, S staterepresenting all schedulable states of the target water conservancy facility under current constraints;

[0038] S34. Defining a feasible solution space based on the structure and operational constraints of the full-life-cycle digital three-dimensional model in the BIM platform:

[0039] satisfying C boundary and being valid within ;

[0040] wherein, is the ith feasible scheduling scheme, and U is a set of all possible scheduling actions;

[0041] S35. Defining a scheduling performance objective function of the optimization model based on actual needs of intelligent scheduling of the target water conservancy facility:

[0042]

[0043] wherein, f level is a water level regulation error function reflecting the degree of satisfaction of the scheduling scheme to the water level regulation target, f flow is a flow optimization control function reflecting the adaptability of the scheduling scheme to flow demand, f delay is a response delay penalty function reflecting the real-time response ability of the scheduling scheme, and w1, w2, w3 are weight coefficients of scheduling targets;

[0044] S36. Integrating the schedulable state S state , the feasible solution space S solution , and the scheduling performance objective function f opt to form a complete optimization framework of the intelligent scheduling problem of the water conservancy facility.

[0045] Optionally, the S4 comprises the following steps:

[0046] S41. Analyzing the criticality and operational sensitivity of each scheduling node of the target water conservancy facility based on the full-life-cycle digital three-dimensional model in the BIM platform, calculating the sensitive weight coefficient η i of each node dynamically according to the physical location, importance level, and environmental impact of the node, defining a node sensitive weight vector, and a high value of the sensitive weight coefficient indicating that the node has a great impact on the overall safe operation and scheduling efficiency of the facility;

[0047] S42. Initializing a control parameter set of the Lévy flight optimization algorithm, the control parameter set including a basic jump step factor α0, a Lévy distribution stability index β, a maximum iteration number T max , and a population size N p , and constructing an initial control parameter set Θ LFO ​;

[0048] S43. According to the feasible solution space S of the optimization model solution and the state space S state , generate an initial candidate solution group:

[0049]

[0050] wherein each initial candidate solution is a set of feasible scheduling strategies that meet the physical structure and operating boundary conditions of the water conservancy facilities;

[0051] S44. Introduce a sensitive weight coefficient η i and an adaptive step size adjustment mechanism for the environmental change rate ζ t The environmental change rate ζ t is calculated by weighting the water level fluctuation rate, flow change trend, and the influence degree of meteorological emergencies in real-time monitoring data, and is used to adjust the algorithm search strategy in real time. The adaptive step size is defined as:

[0052] α i (t)=α0·(1+η i ·ζ t )。

[0053] Optionally, the S5 comprises the following steps:

[0054] S51. In each iteration, based on the current candidate scheduling scheme group X k and the corresponding adaptive step size α i (t), perform Lévy flight jumping operation to generate the next generation candidate scheduling scheme group X k+1 :

[0055]

[0056] wherein, represents the i-th scheduling scheme in the k-th iteration, and the scheduling scheme is composed of a group of adjustable nodes and their operating states, representing a feasible scheduling path of the target water conservancy facility at present, represents the i-th candidate scheduling scheme in the k+1-th iteration, x best represents the current global optimal scheduling solution, α i (t) is the adaptive jumping step size of the i-th node at time t, L β is a random variable subject to Lévy distribution;

[0057] S52. Calculate the scheduling performance objective function of each candidate scheduling scheme

[0058] S53. Call the full life cycle digital three-dimensional model in the BIM platform For each candidate scheduling scheme Physical structure constraint mapping verification is carried out:

[0059]

[0060] Wherein, the function f map (·) judges whether the candidate scheme is executable on the physical layer, including whether there is a structure conflict, path redundancy, scheduling logic violation, and the return value True indicates that the scheme structure is legal;

[0061] S54. For the candidate scheduling scheme whose mapping verification is False, call the structure constraint correction mechanism to carry out local optimization:

[0062]

[0063] Wherein, ∈ i is the perturbation coefficient, γ i is the node semantic weight factor, which is set in combination with the scheduling sensitivity of the node in the BIM model, and the key node is adjusted first, is the gradient direction of the objective function of the candidate scheduling scheme in the local space;

[0064] S55. For all candidate scheduling schemes after mapping verification and local correction Recalculate the scheduling performance objective function value, and compare it with the current global optimal scheduling scheme x best If it meets Then update the global optimal scheduling scheme to

[0065] S56. Repeat S51 to S55 until the maximum iteration number T max is reached, and finally obtain the scheduling scheme set that meets the physical structure, real-time operation state and scheduling target of the water conservancy facility.

[0066] Optionally, the S6 comprises the following steps:

[0067] S61. According to the scheduling performance objective function Comprehensive evaluation is carried out on all structurally legal scheduling schemes in the candidate scheduling scheme group X k+1 According to the following strategy, the global optimal scheduling scheme is selected If all candidate schemes meet the structure constraint and scheduling boundary conditions of the water conservancy facility, the scheme with the minimum objective function value is selected:

[0068]

[0069] If multiple schemes have similar objective function values, i.e., the difference is less than the set threshold, then a second sorting is performed based on equipment scheduling frequency, energy consumption cost and operation complexity, and the scheme with low scheduling operation frequency and simple control action set is selected first.

[0070] If operating in an environment with frequent emergencies, a real-time emergency factor θ is introduced. t The objective function is dynamically adjusted with weights, recalculated, and a scheduling scheme with better responsiveness is selected.

[0071] S62. Select the optimal scheduling scheme Digital 3D model mapped to the entire life cycle of the target water conservancy facility Each scheduling and control node in the BIM model generates a control instruction set U based on the semantic tags and physical connection relationships of each control node. ctrl ;

[0072] S63. Transfer control instruction set U ctrl The data is sent to the target water conservancy facility control system to implement the selected optimal scheduling scheme and activate the operation status monitoring mechanism to record the scheduling results data for subsequent model optimization and scheduling feedback adjustments.

[0073] Optional, the structure expression for the optimal scheduling scheme:

[0074] If the water level warning value h t+Δt h safe And the predicted flow rate q t+Δt >q thresh If this occurs, the emergency control plan will be triggered, and a dispatch path with rapid flood discharge capability will be selected;

[0075] If the water level fluctuation rate If the rainfall is low, environmental parameters are stable, and the predicted rainfall in the next 2 hours is less than the set threshold, then the scheduling scheme with the lowest energy consumption will be selected.

[0076] If there are multiple concurrent task requirements in the target area, the flow allocation priority rule is adopted to meet the downstream irrigation priority scheduling conditions.

[0077] If the current operating frequency of the device exceeds the set maximum operating frequency F op If so, candidate solutions containing excessive operations are eliminated, and path solutions with high structural stability are selected first.

[0078] The beneficial effects of this invention are:

[0079] (1) The application realizes dynamic amplification jump search on the high sensitive area of hydrological emergency by constructing a node sensitive weight vector combined with a real-time environmental change rate, and fine-tuning and correcting the structure stable area, thereby improving the robustness and response speed of the optimization process. In flood control simulation, the mechanism can improve the efficiency of obtaining the global optimal solution and shorten the average response time.

[0080] (2) The application uses the type label, running state and semantic logic of the component in the BIM model to construct a scheduling semantic verification function, performs real-time structure mapping verification on each generation of candidate scheduling scheme, and fine-tunes and corrects illegal scheduling schemes through a local gradient disturbance mechanism guided by semantics, to ensure that all final output scheduling solutions have structure executability.

[0081] (3) The application constructs a state space and a feasible solution space based on the dynamically updated structure information, running state and scheduling boundary of the BIM platform, and designs a multi-objective function integrating water level control accuracy, flow optimization target and response timeliness. In the optimization process, the multi-objective function realizes flexible switching and collaborative balance between scheduling tasks through dynamic weight adjustment. The multi-layer collaborative optimization mechanism is particularly suitable for intelligent scheduling applications of water conservancy facilities in different operation and maintenance stages and functional modes, and effectively supports comprehensive scheduling decisions under complex working conditions. BRIEF DESCRIPTION OF DRAWINGS

[0082] The accompanying drawings are included to provide a further understanding of the application, and constitute a part of the specification, illustrate the application, and are used to explain the application together with the embodiments of the application, and do not constitute a limitation on the application. In the drawings:

[0083] Figure 1 A flowchart of a water conservancy facility intelligent scheduling method based on Lévy flight optimization and BIM is provided. DETAILED DESCRIPTION

[0084] The application will now be described in further detail with reference to the accompanying drawings. These drawings are simplified schematic diagrams, and only illustrate the basic structure of the application in a schematic manner, and therefore only show the components related to the application.

[0085] REFERENCE Figure 1 A water conservancy facility intelligent scheduling method based on Lévy flight optimization and BIM, comprising the following steps:

[0086] S1. Construct a full life cycle digital three-dimensional model of the target water conservancy facility on a BIM platform;

[0087] S2. Collect real-time monitoring data sets of the target water conservancy facility, and perform data mapping between the collected real-time monitoring data sets and the full life cycle digital three-dimensional model, to realize dynamic updating of the full life cycle digital three-dimensional model data;

[0088] S3. Based on the real-time dynamically updated data in the BIM platform, the current operation state information and scheduling boundary conditions of the target water conservancy facility are extracted, and an optimization model of the water conservancy facility scheduling problem is established, forming an optimization framework of the scheduling problem;

[0089] S4. The control parameters of the Lévy flight optimization algorithm are initialized, and an initial solution group is generated according to the scheduling problem optimization model extracted from the BIM platform, and an adaptive step adjustment mechanism based on BIM semantic constraints is introduced;

[0090] S5. The Lévy flight optimization algorithm is used for global search of the scheduling problem, and a random jump and adaptive adjustment mechanism is used to generate multiple candidate scheduling schemes in the optimization model, and each candidate scheduling scheme is mapped and verified through the BIM platform;

[0091] S6. According to the preset scheduling target, the candidate scheduling schemes are comprehensively evaluated, the optimal scheduling scheme is selected, and the selected optimal scheduling scheme is mapped to the control system of the target water conservancy facility to generate corresponding scheduling control instructions.

[0092] In this embodiment, S1 includes the following steps:

[0093] S11. Obtain the engineering design data set of the target water conservancy facility, which includes structural component number, geometric size, material type and spatial position parameters, and use the engineering design data set as the structural basis for constructing the full life cycle digital three-dimensional model, and construct a structural information matrix;

[0094] S12. Access the real-time operation monitoring system of the target water conservancy facility, collect historical and current operation state data sets, including water level monitoring values, flow records, pump station states, gate opening and closing states, and equipment start and stop time operation parameters, and construct an operation state information matrix;

[0095] S13. Based on the real-time environment perception system of the water conservancy facility operation area, collect environmental parameter data sets, including rainfall intensity, evaporation, temperature, wind speed and soil moisture, which are external environmental information affecting the operation of the water conservancy facility, and construct an environmental parameter matrix;

[0096] S14. Extract the key scheduling parameter set, which includes facility operation capacity upper limit, scheduling time window, response delay limit and operation frequency constraint, and construct a key scheduling parameter constraint vector;

[0097] S15. The structural information matrix M structure , the operation state information matrix M status , the environmental parameter matrix M env and the key scheduling parameter constraint vector P keyintegrated into a BIM platform, a full life cycle digital three-dimensional model M of the target water conservancy facility is constructed BIM

[0098] M BIM = <M structure ,M status ,M env ,P key >.

[0099] In this embodiment, S2 includes the following steps:

[0100] S21. Collect real-time monitoring data stream based on real-time monitoring system deployed in water conservancy facility Each piece of data d t includes water level h t , flow q t , equipment state s t , valve state v t and environmental parameter set E t at the current time, and a real-time monitoring data vector is constructed:

[0101] d t = (h t , q t , s t , v t , E t );

[0102] S22. Time label alignment of real-time monitoring data stream D real , structure information matrix M structure and operation state information matrix M status , according to the collection time t, corresponding mapping to the corresponding operation node of the full life cycle digital three-dimensional model M BIM in the BIM platform, a time-state mapping function is constructed:

[0103] f map : d t → M BIM (t);

[0104] Wherein, f map represents a real-time data mapping function, so that each set of real-time monitoring data is injected into the corresponding scheduling unit node;

[0105] S23. Dynamic update of operation state information matrix M status in the BIM platform, new monitoring data vector d t is added to the updated operation state information matrix according to the set time update period:

[0106]

[0107] wherein, represents the running state information matrix before time t, represents the updated state information;

[0108] S24. The updated running state information matrix is injected into the BIM platform in conjunction with the current window data E env of the environmental parameter matrix M t , and the full life cycle digital three-dimensional model is dynamically updated

[0109]

[0110] In this embodiment, S3 includes the following steps:

[0111] S31. Based on the full life cycle digital three-dimensional model updated dynamically in the BIM platform, the running state information of the target water conservancy facility at the current time is extracted, and the current running state information vector is defined, which includes the water level state at the current time, the flow state at the current time, the current equipment running state, the current valve opening and closing state, and the current time environmental parameter set;

[0112] S32. Based on the key scheduling parameter constraint vector P key , the current scheduling boundary condition is extracted, including the upper limit of the scheduling capacity of the target water conservancy facility, the allowed scheduling time window, the response delay limit and the operation frequency constraint, and the scheduling constraint condition set C boundary is constructed;

[0113] S33. According to the running state information vector X t+Δt and the scheduling constraint condition set C boundary , an optimization model of water conservancy facility scheduling problem is established, and the state space of the scheduling scheme is defined as:

[0114]

[0115] wherein, S state represents all schedulable states of the target water conservancy facility under the current constraint condition;

[0116] S34. According to the structure and operation constraints of the full life cycle digital three-dimensional model in the BIM platform, the feasible solution space is defined as:

[0117]

[0118] wherein, is the ith feasible scheduling scheme, and U is the set of all possible scheduling actions;

[0119] S35. Based on the actual demand of the target water conservancy facility intelligent scheduling, define the scheduling performance objective function of the optimization model:

[0120]

[0121] wherein, f level is the water level regulation error function, reflecting the satisfaction degree of the scheduling scheme to the water level regulation target, f flow is the flow optimization control function, reflecting the adaptability of the scheduling scheme to the flow demand, f delay is the response delay penalty function, reflecting the real-time response ability of the scheduling scheme, w1, w2, w3 are the weight coefficients of the scheduling target;

[0122] S36. Comprehensive scheduling state S state , feasible solution space S solution and scheduling performance objective function f opt , build a complete optimization framework of water conservancy facility intelligent scheduling problem.

[0123] In this embodiment, S4 includes the following steps:

[0124] S41. Based on the full life cycle digital three-dimensional model in the BIM platform, analyze the key degree and operation sensitivity of each scheduling node of the target water conservancy facility, according to the physical location, importance level and environmental influence of the node, dynamically calculate the sensitive weight coefficient η i of each node, define the node sensitive weight vector, and the high value of the sensitive weight coefficient represents that the node has great influence on the overall safe operation and scheduling efficiency of the facility;

[0125] S42. Initialize the control parameter set of Lévy flight optimization algorithm, the control parameter set includes basic jump step factor α0, Lévy distribution stability index β, maximum iteration number T max and population size N p , build initial control parameter set Θ LFO ;

[0126] S43. According to the feasible solution space S solution and state space S state of the optimization model, generate initial candidate solution group:

[0127]

[0128] wherein, each initial candidate solution is a kind of feasible scheduling strategy set, which meets the physical structure and operation boundary conditions of the water conservancy facility;

[0129] S44. Introduce the sensitive weight coefficient η iAdaptive step size adjustment mechanism with environment change rate ζ t Adaptive step size adjustment mechanism with environment change rate ζ t By monitoring the water level fluctuation rate, flow change trend and the influence degree of weather emergencies in real time, the adaptive step size is defined as:

[0130] α i (t) = a0 · (1 + η i · ζ t ).

[0131] In this embodiment, S5 includes the following steps:

[0132] S51. In each iteration, based on the current candidate scheduling scheme group X k and the corresponding adaptive step size a i (t), perform Lévy flight jump operation to generate the next generation candidate scheduling scheme group X k+1 :

[0133]

[0134] wherein, represents the i-th scheduling scheme in the k-th iteration, the scheduling scheme is composed of a group of adjustable nodes and their operation states, and represents a feasible scheduling path of the target water conservancy facility at present, represents the i-th candidate scheduling scheme in the k+1-th iteration, x best represents the current global optimal scheduling solution, a i (t) is the adaptive jump step size of the i-th node at time t, L β is a random variable subject to Lévy distribution;

[0135] S52. Calculate the scheduling performance objective function of each candidate scheduling scheme

[0136] S53. Call the full life cycle digital three-dimensional model in the BIM platform to verify the physical structure constraint mapping of each candidate scheduling scheme :

[0137]

[0138] wherein, the function f map (·) judges whether the candidate scheme is executable in the physical layer, including whether there is a structure conflict, path redundancy, scheduling logic violation, and the return value True indicates that the scheme structure is legal when the verification is returned;

[0139] S54. For the candidate scheduling scheme whose mapping verification is False, call the structure constraint correction mechanism to perform local optimization:

[0140]

[0141] where ∈ i is the perturbation coefficient, γ i is the node semantic weight factor, which is set in combination with the scheduling sensitivity of the node in the BIM model, and the key node is adjusted preferentially, is the gradient direction of the objective function of the candidate scheduling scheme in the local space;

[0142] S55. For all candidate scheduling schemes after the mapping verification and local correction , recalculate the scheduling performance objective function value thereof, and compare it with the current global optimal scheduling scheme x best . If , update the global optimal scheduling scheme to x

[0143] S56. Repeat S51 to S55 until the maximum number of iterations T max is reached, and finally obtain the scheduling scheme set that satisfies the physical structure of the water conservancy facility, the real-time operation state, and the scheduling target.

[0144] In this embodiment, S6 includes the following steps:

[0145] S61. According to the scheduling performance objective function , comprehensively evaluate all structurally legal scheduling schemes in the candidate scheduling scheme group X k+1 , and select the global optimal scheduling scheme according to the following strategy If all candidate schemes satisfy the structural constraints and scheduling boundary conditions of the water conservancy facility, select the scheme with the smallest objective function value:

[0146]

[0147] If there are multiple schemes with similar objective function values, that is, the difference is less than a set threshold, then further perform secondary sorting according to the equipment scheduling frequency, energy consumption cost, and operation complexity, and preferentially select the scheme with low scheduling operation frequency and simple control action set;

[0148] If it is operated in a high-frequency emergency environment, introduce a real-time emergency factor θ t to dynamically correct the weight of the objective function, recalculate, and select a more responsive scheduling scheme;

[0149] S62. Map the selected optimal scheduling scheme x to the digital three-dimensional model of the target water conservancy facility throughout its life cycle each scheduling control node in the BIM model, according to the semantic labels and physical connection relationships of each control node in the BIM model, to generate a control instruction set U ctrl ;

[0150] S63. sending the control instruction set U ctrl to the target water conservancy facility control system, implementing landing execution of the selected optimal scheduling scheme, and starting a running state monitoring mechanism to record scheduling result data for subsequent model optimization and scheduling feedback adjustment.

[0151] In this embodiment, the structural expression of the optimal scheduling scheme is:

[0152] If the water level warning value h t+Δt > h safe , and the flow prediction value q t+Δt > q thresh , an emergency control scheme is triggered, and a scheduling path with rapid flood discharge capacity is selected.

[0153] If the water level fluctuation rate is low, the environmental parameters are stable, and the predicted rainfall in the next 2 hours is less than a set threshold, a scheduling scheme with the minimum energy consumption is selected.

[0154] If there are multiple concurrent demands in the target area, a flow allocation priority rule is used to meet the downstream irrigation priority scheduling condition.

[0155] If the current device operating frequency exceeds a set maximum operating frequency F op , the candidate scheme containing excessive operation is excluded, and a path scheme with high structural stability is preferentially selected.

[0156] Embodiment 1:

[0157] This embodiment takes the flood scheduling scene of a river basin in a city in XX Province as the background, and illustrates the feasibility and effectiveness of the present application under actual complex hydrological conditions.

[0158] The river basin covers 2 medium-sized reservoirs, 4 gate control points, and 1 urban drainage station, mainly undertakes regional flood scheduling, urban waterlogging prevention and control, and agricultural irrigation water supplement functions. In recent years, affected by the frequent occurrence of extreme weather, the river basin has frequently appeared problems such as heavy rain, sudden increase of upstream inflow, and linkage and combination of urban waterlogging, causing a series of operation difficulties such as scheduling response lag, high manual operation intensity, and scheduling scheme not adapting to real-time changes. In response to a typical heavy rain warning situation in June 2024, the water conservancy bureau of this region decided to use the scheduling system proposed by the present application for pilot application to replace the traditional scheduling mechanism based on static rule library and manual experience driving, and to explore the deep integration scheduling strategy of intelligent optimization and digital model.

[0159] First, a complete 3D digital model of the water conservancy facilities in the region is established using the BIM platform:

[0160] Structural data of two reservoirs (dam height 35 meters, reservoir capacity 54 million cubic meters, 2 flood discharge gates);

[0161] Operation parameters of four gates (gate width 6 meters, height 4 meters, electric opening and closing control);

[0162] Equipment status of a drainage station (three water pumps, total flow capacity 9000 cubic meters per hour);

[0163] Peripheral terrain, hydrological monitoring points, weather stations, and underground drainage pipe network information;

[0164] Real-time data interface access: water level, water pump operation, rainfall, wind speed, flow rate;

[0165] Historical operation data covering nearly three years (January 2021 to April 2024);

[0166] At 12:00 on June 7, 2024, according to the forecast of the meteorological department, there will be a regional heavy rain in the next 24 hours, with a predicted rainfall of 210 mm, belonging to the III-grade rainstorm warning standard, the model automatically triggers the intelligent scheduling module. At this time, the system accesses real-time monitoring data and detects the following parameters:

[0167] The upstream water level rises to 28.3 meters (the warning water level is 29 meters);

[0168] The downstream city drainage station has started 1 water pump, and the flow rate is 2.1 m 3 / s;

[0169] The current weather forecast shows that the rain will reach its peak in 3 hours and last for 8 hours;

[0170] In the data preparation stage, the platform updates the BIM model according to the monitoring data, completes the joint modeling of the current structure state, operation state and environment state of the water conservancy facilities, and automatically extracts the scheduling constraints. The discharge allowed period is 14:00-02:00, the reservoir water release frequency limit is not more than 1 time every 4 hours, and the continuous working time of a single pump of the drainage station should not exceed 3 hours.

[0171] Subsequently, the system starts the Lévy flight optimization module to conduct global search on the scheduling state space and candidate schemes. The node sensitivity weight introduced in this process is as follows:

[0172] The upstream reservoir node sensitivity weight is 0.85 (because it directly affects the change of downstream water level);

[0173] The node sensitivity weight of the urban drainage pump station is 0.78 (because of high urban waterlogging influence);

[0174] The gate node sensitivity weight is between 0.6-0.72;

[0175] Combined with the real-time water level change rate (increased by 0.5 meters in nearly 1 hour), the system dynamically adjusts and optimizes the jump step, improves the search intensity of the high-sensitive node, generates 500 groups of feasible scheduling strategies in the initial population, and converges to the optimal scheduling solution after 400 iterations.

[0176] The optimal scheduling strategy result is as follows:

[0177] 14:30 Start the first flood discharge gate of the upstream reservoir, discharge flow 800 m 3 / s;

[0178] 15:00-15:30 Start the second water pump of the urban drainage station (total flow 6000 m 3 / h);

[0179] 16:30-17:30 Start the downstream gate #3 to open 60%, to ensure safe drainage of the agricultural irrigation area;

[0180] 21:00 Close the reservoir gate and switch to the storage mode to deal with subsequent continuous rainfall;

[0181] The scheduling instruction set is mapped and verified by the BIM model, which meets all the device operating conditions and control logic, and the instructions are directly issued to the reservoir scheduling control system and the drainage station PLC device.

[0182] In order to verify the performance difference between the method of the application and the traditional method, a simulation comparison test for 3 days is carried out, the same initial boundary conditions are set, and the scheduling target is to maximize the reduction of flood peak water level and shorten the water accumulation time, and the results are as follows:

[0183]

[0184] In addition, sample analysis shows that the method of the application has more obvious optimization effect on scenes with complex structure and high coupling degree of scheduling logic. In the past 10 hydrological event samples (respectively from the rainstorm flood cases in 2022-2024), the scheduling failure rate can be reduced by 62% on average by using the scheduling system of the application, and the operation and debugging time is shortened by about 41%, which significantly improves the intelligent response ability and scheduling effectiveness of the system.

[0185] In summary, the embodiment fully demonstrates the operation process, algorithm response process and execution effect of the application in the actual intelligent scheduling scene of water conservancy facilities, and fully verifies the superiority of the method of the application in structure constraint adaptability, scheduling real-time performance and execution feasibility compared with the prior art.

[0186] The application realizes dynamic amplification jump search on the high sensitive area of hydrological emergency (heavy rainfall, water level rising) by constructing node sensitive weight vector combined with real-time environmental change rate, and fine-tunes and corrects the stable structure area, thereby improving the robustness and response speed of the optimization process. In the flood control simulation, the mechanism can improve the efficiency of obtaining global optimal solution and shorten the average response time.

[0187] The application uses the type label, running state and semantic logic of the component in the BIM model to construct a scheduling semantic verification function, performs real-time structure mapping verification on each generation of candidate scheduling scheme, and fine-tunes and corrects the illegal scheduling scheme through the local gradient disturbance mechanism guided by semantics, so as to ensure that all final output scheduling solutions have structure executability.

[0188] The application constructs state space and feasible solution space based on the dynamic updated structure information, running state and scheduling boundary of the BIM platform, designs a multi-objective function integrating water level control accuracy, flow optimization target and response timeliness, realizes flexible switching and collaborative balance among scheduling tasks through dynamic weight adjustment in the optimization process, and the multi-layer collaborative optimization mechanism is especially suitable for intelligent scheduling application of water conservancy facilities in different operation and maintenance stages and function modes, and effectively supports comprehensive scheduling decision under complex working conditions.

[0189] The above is only the preferred specific embodiment of the application, but the protection scope of the application is not limited to this, any person skilled in the art can make equivalent replacement or change according to the technical scheme and the inventive concept of the application within the technical range disclosed by the application, which should be covered in the protection scope of the application.

Claims

1. A method for intelligent scheduling of water conservancy facilities based on Lévy flight optimization and BIM, characterized in that, Includes the following steps: S1. Construct a digital 3D model of the target water conservancy facility throughout its entire lifecycle on a BIM platform; S2. Collect real-time monitoring datasets of the target water conservancy facilities, and map the collected real-time monitoring datasets with the full life cycle digital 3D model to achieve dynamic updates of the full life cycle digital 3D model data; S3. Based on the real-time dynamic updates of data in the BIM platform, extract the current operating status information and scheduling boundary conditions of the target water conservancy facilities, and establish an optimization model for the water conservancy facility scheduling problem to form an optimization framework for the scheduling problem; S4. Initialize the control parameters of the Lévy flight optimization algorithm, and generate an initial solution group based on the scheduling problem optimization model extracted from the BIM platform. At the same time, introduce an adaptive step size adjustment mechanism based on BIM semantic constraints. S5. The Lévy flight optimization algorithm is used to perform a global search for the scheduling problem. Multiple candidate scheduling schemes are generated in the optimization model by using random jump and adaptive adjustment mechanisms. The candidate scheduling schemes are then mapped and verified through the BIM platform. S6. Based on the preset scheduling objectives, comprehensively evaluate the candidate scheduling schemes, select the optimal scheduling scheme, and map the selected optimal scheduling scheme to the control system of the target water conservancy facility to generate corresponding scheduling control commands; S4 includes the following steps: S41. Full lifecycle digital 3D model based on BIM platform The criticality and operational sensitivity of each scheduling node of the target water conservancy facility are analyzed. Based on the physical location, importance level, and environmental impact of the nodes, the sensitivity weight coefficient of each node is dynamically calculated. Define a node sensitivity weight vector. A high sensitivity weight coefficient indicates that the node has a significant impact on the overall safe operation and scheduling efficiency of the facility. S42. Initialize the control parameter set for the Lévy flight optimization algorithm. The control parameter set includes the basic jump step size factor. Lévy distribution stability index Maximum number of iterations and population size Construct the initial control parameter set ; S43. Based on the feasible solution space of the optimization model With state space Generate initial candidate solution groups: ； Among them, each initial candidate solution This is a feasible set of scheduling strategies that satisfies the physical structure and operational boundary conditions of water conservancy facilities; S44. Introducing Sensitive Weighting Coefficient With environmental change rate The adaptive step size adjustment mechanism, environmental change rate The algorithm's search strategy is adjusted in real time by weighting the impact of water level fluctuation rate, flow rate change trend, and meteorological emergencies in real-time monitoring data. The adaptive step size is defined as follows: 。 2. The intelligent scheduling method for water conservancy facilities based on Lévy flight optimization and BIM according to claim 1, characterized in that, S1 includes the following steps: S11. Obtain the engineering design dataset of the target water conservancy facility. The engineering design dataset includes structural component numbers, geometric dimensions, material types, and spatial location parameters. Use the engineering design dataset as the structural basis for constructing a full life cycle digital three-dimensional model and construct a structural information matrix. S12. Connect to the real-time operation monitoring system of the target water conservancy facility, collect historical and current operation status datasets, including water level monitoring values, flow records, pump station status, gate opening and closing status, and equipment start-up and shutdown time operation parameters, and construct an operation status information matrix; S13. Based on the real-time environmental perception system of the water conservancy facility operation area, collect environmental parameter datasets, including external environmental information on the impact of rainfall intensity, evaporation, temperature, wind speed and soil moisture on the operation of water conservancy facilities, and construct an environmental parameter matrix; S14. Extract the set of key scheduling parameters, which includes facility operating capacity limit, scheduling time window, response delay limit and operation frequency constraint, and create a key scheduling parameter constraint vector. S15. Transfer the structural information matrix Operating status information matrix Environmental parameter matrix and key scheduling parameter constraint vectors Integrate into the BIM platform to build a digital 3D model of the target water conservancy facility throughout its entire lifecycle. : 。 3. The intelligent scheduling method for water conservancy facilities based on Lévy flight optimization and BIM according to claim 1, characterized in that, S2 includes the following steps: S21. Real-time monitoring system based on water conservancy facility deployment collects real-time monitoring data streams. Each of these data points Including the current water level ,flow Equipment status Valve status and environmental parameter set Construct real-time monitoring data vectors: ； S22. Transfer the real-time monitoring data stream With structural information matrix and running status information matrix Perform time tag alignment based on collection time. This corresponds to the full lifecycle digital 3D model mapped to the BIM platform. For the corresponding running node, construct the time-state mapping function: ； in, This represents a real-time data mapping function that injects each set of real-time monitoring data into the corresponding scheduling unit node; S23. Operational status information matrix in the BIM platform Dynamic updates are performed, and new monitoring data vectors are updated according to the set time update cycle. Add the updated runtime status information matrix: ； in, Indicates time The previous running status information matrix, This represents the updated runtime status information matrix; S24. Update the running status information matrix With environmental parameter matrix Current window data The data is integrated into the BIM platform and dynamically updated throughout the entire lifecycle of the digital 3D model. : 。 4. The intelligent scheduling method for water conservancy facilities based on Lévy flight optimization and BIM according to claim 1, characterized in that, S3 includes the following steps: S31. A dynamically updated, full-lifecycle digital 3D model based on a BIM platform. Extract the current operating status information of the target water conservancy facility, define the current operating status information vector, which includes the current water level status, the current flow rate status, the current equipment operating status, the current valve opening and closing status, and the current environmental parameter set. S32. Based on key scheduling parameter constraint vectors Extract the current scheduling boundary conditions, including the upper limit of the scheduling capacity of the target water conservancy facility, the allowable scheduling time window, the response delay limit, and the operation frequency constraint, and construct a set of scheduling constraints. ; S33. Based on the aforementioned operating status information vector With the set of scheduling constraints An optimization model for the water conservancy facility scheduling problem is established. The optimization model defines the state space of the scheduling scheme as follows: ； in, This represents all dispatchable states of the target water conservancy facility under the current constraints; S34. Based on the full lifecycle digital 3D model in the BIM platform Given the structural and operational constraints, define the feasible solution space: ； in, For the first A feasible scheduling scheme The set of all possible scheduling actions; S35. Based on the actual needs of intelligent scheduling of target water conservancy facilities, define the scheduling performance objective function of the optimization model: ； in, Let be the water level control error function, reflecting the degree to which the scheduling scheme meets the water level control target. The flow optimization control function reflects the adaptability of the scheduling scheme to flow demand. The delay penalty function reflects the real-time response capability of the scheduling scheme. The weighting coefficients for the scheduling targets; S36. Overall Scheduling Status Feasible solution space With scheduling performance objective function A complete optimization framework for the intelligent scheduling of water conservancy facilities will be constructed.

5. The intelligent scheduling method for water conservancy facilities based on Lévy flight optimization and BIM according to claim 4, characterized in that, S5 includes the following steps: S51. In each iteration, based on the current group of candidate scheduling schemes... With the corresponding adaptive step size Execute Lévy flight hop operations to generate a group of next-generation candidate scheduling schemes. : ； in, Indicates the first In the nth iteration Each scheduling scheme consists of a set of adjustable points and their operational states, representing a feasible scheduling path for the target water conservancy facility at present. Indicates the first In the nth iteration One candidate scheduling scheme, This represents the current globally optimal scheduling scheme. Let be a random variable that follows a Lévy distribution; S52. For each generated candidate scheduling scheme Calculate its scheduling performance objective function ; S53. Calling the full lifecycle digital 3D model in the BIM platform For each candidate scheduling scheme Perform physical structure constraint mapping verification: ； Among them, the function Determine whether the candidate solution is physically executable, including whether there are structural conflicts, path redundancy, or scheduling logic violations. A return value of True indicates that the solution structure is valid. S54. For candidate scheduling schemes where the mapping verification is False, invoke the structural constraint correction mechanism for local optimization: ； in, For perturbation coefficients, As a semantic weighting factor for nodes, combined with the scheduling sensitivity settings of nodes in the BIM model, priority is given to adjusting key nodes. This represents the gradient direction of the objective function of the candidate scheduling scheme in the local space. S55. For all candidate scheduling schemes after mapping verification and local correction. Recalculate its scheduling performance objective function value and compare it with the current globally optimal scheduling scheme. Compare, if satisfied Then update the current globally optimal scheduling scheme to ; S56. Repeat steps S51 to S55 until the maximum number of iterations is reached. Ultimately, a set of scheduling schemes that meet the physical structure, real-time operating status, and scheduling objectives of water conservancy facilities is obtained.

6. The intelligent scheduling method for water conservancy facilities based on Lévy flight optimization and BIM according to claim 5, characterized in that, S6 includes the following steps: S61. Based on the scheduling performance objective function Next-generation candidate scheduling scheme group A comprehensive evaluation of all valid scheduling schemes is conducted, and the globally optimal scheduling scheme is selected based on the following strategy. If all candidate schemes satisfy the structural constraints and scheduling boundary conditions of the water conservancy facilities, select the scheme with the minimum objective function value. ； If multiple schemes have similar objective function values ​​and the difference is less than a set threshold, then a second sorting is performed based on equipment scheduling frequency, energy consumption cost and operation complexity, and the scheme with low scheduling operation frequency and simple control action set is selected first. If operating in an environment with frequent emergencies, a real-time emergency response factor should be introduced. The objective function is dynamically adjusted with weights, recalculated, and a scheduling scheme with better responsiveness is selected. S62. Select the optimal scheduling scheme Digital 3D model mapped to the entire life cycle of the target water conservancy facility Each scheduling and control node in the BIM model generates a set of control instructions based on the semantic tags and physical connections of each control node in the BIM model. ; S63. Control instruction set The data is sent to the target water conservancy facility control system to implement the selected optimal scheduling scheme and activate the operation status monitoring mechanism to record the scheduling results data for subsequent model optimization and scheduling feedback adjustments.

7. The intelligent scheduling method for water conservancy facilities based on Lévy flight optimization and BIM according to claim 6, characterized in that, The structural expression of the optimal scheduling scheme: If the water level warning value And traffic forecast value If this occurs, the emergency control plan will be triggered, and a dispatch path with rapid flood discharge capability will be selected; If the water level fluctuation rate If the rainfall is low, environmental parameters are stable, and the predicted rainfall in the next 2 hours is less than the set threshold, then the scheduling scheme with the lowest energy consumption will be selected. If there are multiple concurrent task requirements in the target area, the flow allocation priority rule is adopted to meet the downstream irrigation priority scheduling conditions. If the current operating frequency of the device exceeds the set maximum operating frequency If so, candidate solutions containing excessive operations are eliminated, and path solutions with high structural stability are selected first.

Images